MasterControl Seventeen Every Time
Governed enterprise analytics study shows deterministic policy execution matched 110/110 answer-and-evidence contracts while runtime agent planning matched none.
The paper studies a governed approach where a language model interprets the question while deterministic policy selects and runs a pre-approved analytical program returning results and evidence. Across 440 runs, three 8B models generated SQL and selected tools at runtime, while Qwen3-8B only interpreted intent and policy executed the approved program. None of 330 runtime-planning episodes satisfied the full answer-and-evidence contract, whereas the policy-executed analyzer matched 110 of 110. The authors note this is configuration-specific and expressiveness is preserved via relational operations, aggregation, comparison, windows, ranking, and similarity with replayable results.
- LLM interprets intent while deterministic policy executes pre-approved analytical programs
- 440-run evaluation across three 8B models and Qwen3-8B intent interpretation
- Policy execution matched 110/110 contracts; 0 of 330 runtime-planning episodes matched
- Restricted analytics remain expressive via relational ops, aggregation, windows, and ranking
- AI models
- Qwen3-8B
From the original article
1 min read at huggingface.co
We study a governed approach to enterprise analytics: a language model interprets the question, while deterministic policy selects and runs a pre-approved analytical program that returns both results and evidence. We show that this restriction can remain expressive within a defined analytical class, using relational operations plus aggregation, comparison, windows, ranking, and similarity.
By MasterControl AI Lab · huggingface.co
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.